OpenAI: GPT-3.5 Turbo Instruct

Text input Text output
Author's Description

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Key Specifications
Cost
$$$$
Context
4K
Parameters
175B
Released
Sep 27, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logit Bias Max Tokens Presence Penalty Seed Frequency Penalty Top P Top Logprobs Temperature Response Format Stop Logprobs
Features

This model supports the following features:

Response Format
Performance Summary

OpenAI's GPT-3.5 Turbo Instruct, created on September 27, 2023, and trained on data up to September 2021, is a variant of GPT-3.5 Turbo specifically tuned for instructional prompts. This model consistently performs among the fastest models, ranking in the 81st percentile for speed across five benchmarks. It offers moderate pricing, placing in the 33rd percentile for cost. A significant strength is its exceptional reliability, demonstrating minimal technical failures and ranking in the 99th percentile. In terms of benchmark performance, the model shows varied capabilities. It achieved 71.0% accuracy in Coding (Baseline) and 38.0% in Instruction Following (Baseline), both ranking in the 37th percentile for accuracy. Its Reasoning (Baseline) performance was 39.0% accuracy, placing it in the 25th percentile. However, it demonstrated strong performance in Ethics (Baseline) with 97.0% accuracy (35th percentile) and General Knowledge (Baseline) with 93.5% accuracy (42nd percentile). While its speed is a consistent advantage across all benchmarks, its accuracy in complex reasoning and instruction following tasks appears to be a notable weakness. Its strengths lie in its high reliability, speed, and solid performance in general knowledge and ethical reasoning.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.5
Completion $2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-3.5-turbo-instruct 4K $1.5 / 1M tokens $2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by openai